Secrecy keeping method and system based on artificial intelligence and terminal

Abstract

The invention relates to a secrecy method, system and terminal based on artificial intelligence, and relates to the field of information security technology, and the method comprises the steps: obtaining a secrecy image in a preset secrecy area; judging whether the camera is shielded or not according to the confidential image; when the camera is shielded, controlling a preset secrecy device to send a preset shielding warning; when the camera is not shielded, judging whether camera equipment exists or not according to the confidential image; and when the camera equipment exists, controlling a preset confidentiality device to send a preset leakage alarm. The method and the device have the effects of improving the security of the information and reducing the situation that the information is leaked from the outside.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a confidentiality method, system and terminal based on artificial intelligence. Background Art

[0002] Confidentiality methods refer to technical means used to protect information systems and data from unauthorized access, use, disclosure, destruction or interference.

[0003] In the prior art, enterprises or institutions with confidentiality requirements often have internal information confidentiality systems, which generally use encryption technology, firewall technology, identity authentication technology and other technologies to prevent information leakage within the system.

[0004] In scenarios where confidential information needs to be read, devices with camera functions, such as mobile phones carried by personnel, can easily record confidential information through images, causing the information to leak from outside the confidentiality system. Summary of the invention

[0005] In order to improve the security of information and reduce the leakage of information from the outside, the present invention provides a confidentiality method, system and terminal based on artificial intelligence.

[0006] In a first aspect, the present invention provides a confidentiality method based on artificial intelligence, which adopts the following technical solution:

[0007] An artificial intelligence-based confidentiality method comprising:

[0008] Acquire a confidential image within a preset confidential area;

[0009] Determine whether the camera is blocked based on the confidential image;

[0010] When the camera is blocked, the preset security device is controlled to issue a preset blocking warning;

[0011] When the camera is not blocked, determine whether there is a camera device based on the confidential image;

[0012] When there is a camera device, the preset security device is controlled to issue a preset leakage warning.

[0013] By adopting the above technical solution, images are obtained in real time through the camera in scenarios where leakage prevention is required, so that the behavior of people can be judged based on the images, and then the confidentiality device can be controlled to hide confidential information when people make sensitive behaviors such as covering the camera or taking out the camera equipment, thereby reducing the situation where confidential information is leaked to the outside due to being photographed, and improving the security of information.

[0014] Optionally, also include:

[0015] Control the preset security device to obtain network parameters;

[0016] Determine whether the security device is disconnected from the network based on network parameters;

[0017] When the security device is disconnected from the network, the preset security device is controlled to issue a preset disconnection warning;

[0018] When the security device is not disconnected from the network, the preset security device is controlled to obtain display parameters;

[0019] Determine the display number according to the display parameters;

[0020] Determine confidentiality level based on display number;

[0021] When the confidentiality level is lower than a preset display threshold, the preset confidentiality device is controlled to issue a preset leakage warning.

[0022] By adopting the above technical solution, the network status and display status of the confidentiality device are monitored in real time, so that when the network connection of the confidentiality device is disconnected or the display device is replaced, the confidentiality device is controlled to hide confidential information, reducing the situation of information leakage caused by tampering with the confidentiality device and improving information security.

[0023] Optionally, a leakage handling method is also included, and the leakage handling method includes:

[0024] When the preset security device issues a preset leakage warning, obtaining the security number currently displayed by the preset security device;

[0025] Determine whether the facial features of the leaker can be extracted based on the confidential image;

[0026] When the facial features of the leaker can be extracted, the leaking features of the leaker are determined based on the confidential image;

[0027] Determine the breach based on confidential images;

[0028] Record confidentiality numbers, leakage characteristics and leakage behaviors in the preset leakage record table.

[0029] By adopting the above technical solution, when a person leaks information, the facial features of the person are extracted from the image and stored to facilitate the subsequent tracking of the leaker, thereby reducing the number of internal leaks and improving information security.

[0030] Optionally, the leakage handling method further includes:

[0031] When the facial features of the leaker cannot be extracted, the sound information in the preset confidential area is obtained;

[0032] Determine whether acoustic features can be extracted based on the sound information;

[0033] When the acoustic features can be extracted, the leaking features of the leaker are determined based on the sound information;

[0034] When the acoustic feature cannot be extracted, the region number of the confidentiality region is determined based on the confidentiality image;

[0035] Determine the closing number based on the area number;

[0036] The preset electric switch is controlled according to the closing number to close the entrance and exit preset in the confidential area.

[0037] By adopting the above technical solution, when the facial features of a person cannot be extracted from the image, the acoustic features of the person are extracted from the sound information of the confidential area, and when the acoustic feature extraction fails, it is judged that the probability of leakage of the person is relatively high. At this time, the electric control switch is controlled to close the confidential area to wait for the person to handle it, thereby reducing the situation of personnel leakage and improving the security of information.

[0038] Optionally, the leakage handling method further includes:

[0039] After closing the entrance and exit, obtain the security image outside the entrance and exit;

[0040] Determine whether there are people outside the entrance or exit based on the security image;

[0041] When there is a person outside the entrance or exit, the unlocking feature is determined based on the security image;

[0042] Determine security level based on unlocking characteristics;

[0043] When the security level is not lower than the preset access threshold, the unlocking number is determined according to the unlocking feature, and the preset electric control switch is controlled to open the entrance and exit preset in the confidential area according to the closing number;

[0044] Record the confidentiality number and unlocking number in the preset unlocking record table.

[0045] By adopting the above technical solution, when the confidential area is closed, the facial features of the people coming for processing are extracted through images, so as to determine the identity of the people coming, and then the electric switch is controlled to lift the blockade when the management personnel come, so as to facilitate the management personnel to deal with the people suspected of leaking secrets.

[0046] Optionally, the leakage handling method further includes:

[0047] Obtaining confidential information;

[0048] Determine the leak number based on the leak information;

[0049] Find out the leakage characteristics from the preset leakage record table according to the leakage number;

[0050] Determine the main suspect number based on the characteristics of the leak;

[0051] Find the secondary suspect number from the preset unlocking record table according to the leak number;

[0052] Generate suspected leak information based on the main suspect number and the secondary suspect number;

[0053] The suspected persons are displayed according to the preset management device of the suspected information leakage control.

[0054] By adopting the above technical solution, when information is leaked, the information of the person suspected of leaking the information is searched from the pre-recorded leakage record table and unlocking record table according to the leaked information, so as to match the suspected persons with greater suspicion, thereby improving the convenience of information leakage processing.

[0055] Optionally, a gesture recognition method is also included, and the gesture recognition method includes:

[0056] When the camera is blocked, the preset radio wave device is controlled to send out preset distance measuring radio waves, and the preset radio wave device is controlled to receive feedback radio waves;

[0057] Determine the personnel's posture and position based on the feedback radio waves;

[0058] When the person's position falls into the preset operation range, determine whether the person is holding a suspicious device based on the person's posture;

[0059] When a person holds a suspected device, the preset confidentiality device is controlled to issue a preset leakage warning;

[0060] When the person is not holding the suspected device, determine the operating position of the person's hand based on the person's posture;

[0061] When the operating position does not fall within the preset hand interval, the preset security device is controlled to issue a preset leakage warning.

[0062] By adopting the above technical solution, when the camera is blocked, the position and posture of the person are identified through electromagnetic waves, so as to judge the person's behavior, and then control the confidentiality device to hide confidential information when the person performs sensitive behavior, thereby reducing information leakage.

[0063] Optionally, a communication interference method is also included, and the communication interference method includes:

[0064] When a person is holding a suspected device, determine the direction of the launch based on the person's position;

[0065] Control the preset radio wave device to turn according to the emission direction, and determine the device size of the suspected device according to the posture of the personnel;

[0066] Determine the interference frequency based on the size of the equipment;

[0067] The preset radio wave device is controlled to emit interference radio waves according to the interference frequency.

[0068] By adopting the above technical solution, when a person is identified as holding a suspicious device through electromagnetic waves, the power of the device is judged according to the size of the device held by the person, so as to control the radio wave device to emit higher frequency electromagnetic waves to interfere with the device held by the person, thereby reducing information leakage.

[0069] In the second aspect, the present application provides a confidentiality system based on artificial intelligence, which adopts the following technical solutions:

[0070] An artificial intelligence-based confidentiality system, comprising:

[0071] An acquisition module is used to acquire confidential images, network parameters, display parameters, confidential numbers, sound information, security images and leaked information;

[0072] A memory for storing a program of any one of the above-mentioned artificial intelligence-based confidentiality methods;

[0073] The program in the memory can be loaded and executed by the processor.

[0074] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution:

[0075] An intelligent terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any of the above-mentioned artificial intelligence-based confidentiality methods.

[0076] By adopting the above technical solution, images are obtained in real time through the camera in scenarios where leakage prevention is required, so that the behavior of people can be judged based on the images, and then the confidentiality device can be controlled to hide confidential information when people make sensitive behaviors such as covering the camera or taking out the camera equipment, thereby reducing the situation where confidential information is leaked to the outside due to being photographed, and improving the security of information.

[0077] In summary, the present application includes at least one of the following beneficial technical effects:

[0078] 1. In scenarios where leakage prevention is required, images are obtained in real time through cameras, and the behavior of personnel is judged based on the images. When personnel make sensitive behaviors such as covering the camera or taking out the camera, the confidentiality device is controlled to hide the confidential information, thereby reducing the situation where confidential information is photographed and leaked from the outside, and improving the security of information;

[0079] 2. Real-time monitoring of the network status and display status of the security device, so as to control the security device to hide confidential information when the network connection of the security device is disconnected or the display device is replaced, reduce the situation of information leakage caused by tampering of the security device, and improve the security of information;

[0080] 3. When a person leaks information, the person’s facial features are extracted from the image and stored to facilitate subsequent tracking of the leaker, thereby reducing the number of internal leaks and improving information security. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a process based on artificial intelligence confidentiality method Figure 1 ;

[0082] Figure 2 It is a process based on artificial intelligence confidentiality method Figure 2 ;

[0083] Figure 3 Is the process of leak handling method Figure 1 ;

[0084] Figure 4 Is the process of leak handling method Figure 2 ;

[0085] Figure 5 Is the process of leak handling method Figure 3 ;

[0086] Figure 6 Is the process of leak handling method Figure 4 ;

[0087] Figure 7 is a flow chart of the gesture recognition method;

[0088] Figure 8 It is a flow chart of the communication jamming method. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0090] The embodiment of the present application discloses a confidentiality method based on artificial intelligence. The present invention detects shooting behavior through technical means, which not only effectively prevents the leakage of confidential information, but also records the leakage behavior to achieve a deterrent effect, thereby reducing information leakage and improving information security.

[0091] Reference Figure 1 , an artificial intelligence-based confidentiality method, including:

[0092] Step 100: Acquire a confidential image within a preset confidential area.

[0093] The confidentiality area refers to a pre-set scene that needs to prevent information leakage. The confidentiality area is selected by the staff according to the actual situation and will not be described in detail here. The confidentiality image is the picture in the confidentiality area. The confidentiality image can be obtained through the camera. The method of obtaining the confidentiality image is selected by the staff according to the actual situation and will not be described in detail here.

[0094] Step 101: Determine whether the camera is blocked according to the confidential image.

[0095] Whether there is an obstruction in front of the camera can be determined by judging the objects shown in the confidential image to determine whether the camera is blocked. Image recognition technology can be used to determine whether the camera is blocked. The method for determining occlusion is common knowledge among people in this field and will not be elaborated here.

[0096] Step 102: When the camera is blocked, a preset security device is controlled to issue a preset blocking warning.

[0097] The confidentiality device refers to a device used to display confidential information. The confidentiality device can be a drawing machine or a computer. The blocking warning refers to the information used by the confidentiality device to hide confidential information and notify personnel when the camera is blocked. The confidentiality device and blocking warning are selected by the staff according to the actual situation, and will not be described here. The camera is blocked, which means that the camera cannot monitor the behavior of people in the confidential area. At this time, there is a risk of leakage. It is necessary to control the confidentiality device to issue a blocking warning to hide confidential information and notify personnel when the camera is blocked.

[0098] Step 103: When the camera is not blocked, determine whether there is a camera device based on the confidential image.

[0099] A camera device refers to a device with a camera function such as a mobile phone or a camera. Image recognition technology can be used to determine whether a camera device exists in a confidential image. The recognition method of a camera device is common knowledge among people in this field and will not be elaborated here.

[0100] Step 104: When there is a camera device, control the preset security device to issue a preset leakage warning.

[0101] Leakage warning refers to information used by confidentiality devices to hide confidential information and warn personnel to stop sensitive behaviors. Leakage warning is selected by staff according to actual conditions and will not be described in detail here. If a camera device is present, the representative personnel has taken out the camera device. At this time, there is a risk of leakage. It is necessary to control the confidentiality device to issue a leak warning to hide confidential information and warn personnel to stop sensitive behaviors, thereby reducing information leakage.

[0102] Reference Figure 2, an artificial intelligence-based confidentiality method, further comprising:

[0103] Step 105: Control the preset security device to obtain network parameters.

[0104] Network parameters refer to data such as network speed and delay that are used to reflect the network status of the security device. The method for obtaining network parameters is selected by the staff based on actual conditions and will not be elaborated here.

[0105] Step 106: Determine whether the security device is disconnected from the network based on the network parameters.

[0106] The network status of the security device can be determined by the numerical value of the network parameter. The method for determining network disconnection is common knowledge among those skilled in the art and will not be described in detail here.

[0107] Step 107: When the security device is disconnected from the network, the preset security device is controlled to issue a preset disconnection warning.

[0108] The network disconnection warning is a message used by the security device to hide confidential information and remind personnel to check the network connection. The network disconnection warning is selected by the staff according to the actual situation and will not be described here. The network disconnection of the security device means that the security device is disconnected from the external network. At this time, it is difficult for the security device to resist the external intrusion in time, and there is a risk of leakage. It is necessary to control the security device to issue a network disconnection warning to hide confidential information and remind personnel to check the network connection.

[0109] Step 108: When the security device is not disconnected from the network, control the preset security device to obtain display parameters.

[0110] Display parameters refer to the model, serial number, production date and other parameters of the display of the confidentiality device. Confidential information is generally read through the confidentiality device and transmitted to the display through a data cable for display to personnel. The display parameters can be read directly through the confidentiality device. The method of obtaining the display parameters is selected by the staff according to the actual situation and will not be elaborated here.

[0111] Step 109: Determine the display number according to the display parameters.

[0112] The display number refers to a number set manually to distinguish displays. The display parameters corresponding to the display parameters can be queried from the display number correspondence table. The display parameter correspondence table refers to a data table that records the display parameters and their corresponding display numbers in advance.

[0113] Step 110: Determine the confidentiality level according to the display number.

[0114] The confidentiality level refers to an artificially set value used to reflect the security performance of the display. The confidentiality level can be obtained from the confidentiality level correspondence table. The confidentiality level correspondence table refers to a data table that records the display number and its corresponding confidentiality level in advance. When there is no consistent display number in the confidentiality level correspondence table, the confidentiality level is defined as the lowest.

[0115] Step 111: When the confidentiality level is lower than a preset display threshold, a preset confidentiality device is controlled to issue a preset leakage warning.

[0116] The display threshold refers to the pre-set minimum confidentiality level of the display that is allowed to display confidential information. The display threshold is selected by the staff according to the actual situation and will not be elaborated here. If the confidentiality level is lower than the display threshold, it means that the display connected to the confidentiality device has low security performance. That is, if the staff disconnects the confidentiality device from the original display and connects the confidentiality device to a new display with lower security performance, there is a risk of confidential information leakage. It is necessary to control the confidentiality device to issue a leakage warning to hide confidential information and warn the staff to stop sensitive behavior, thereby reducing information leakage.

[0117] Reference Figure 3 , the leak handling methods include:

[0118] Step 200: When the preset security device issues a preset leakage warning, the security number currently displayed by the preset security device is obtained.

[0119] The confidentiality number refers to a number set manually to distinguish confidential information. The confidentiality number can be directly read through a confidentiality device. The method of reading the confidentiality number is common knowledge among people in this field and will not be elaborated here.

[0120] Step 201: Determine whether the facial features of the leaker can be extracted based on the confidential image.

[0121] Facial features refer to features used for face recognition. Face recognition technology can be used to determine whether the facial features of a leaker can be extracted. The method for identifying facial features is common knowledge among people in this field and will not be elaborated here.

[0122] Step 202: When the facial features of the leaker can be extracted, the leaking features of the leaker are determined based on the confidential image.

[0123] The leakage feature refers to the feature of the person suspected of leaking secrets. The leakage feature can be a facial feature or an acoustic feature. When the facial feature is used as the leakage feature, it can be obtained through face recognition technology. When the acoustic feature is used as the leakage feature, it can be obtained through voice recognition technology. The method for determining the leakage feature is common knowledge among people in the field and will not be described in detail here. The ability to extract the facial features of the leaker means that the face of the leaker can be identified at this time, and the facial features of the leaker are directly extracted from the confidential image through face recognition technology as the leakage feature.

[0124] Step 203: Determine the leakage behavior according to the confidential image.

[0125] Leakage behavior refers to the behavior of the person suspected of leaking information, namely the above-mentioned handheld camera equipment and modified display behavior. The leakage behavior can be identified from the confidential image through gesture recognition technology, and the behavior that triggers the alarm can also be directly read from the system as the leakage behavior. The method of identifying leakage behavior is common knowledge among people in this field and will not be elaborated here.

[0126] Step 204: Record the confidentiality number, leakage characteristics and leakage behavior into a preset leakage record table.

[0127] The leak record sheet refers to a data sheet used to record the leaks of persons who have committed the leaks. The leak record sheet is used to facilitate the subsequent handling of the leaks, achieve a deterrent effect, and reduce the number of leaks.

[0128] Reference Figure 4 , the leak handling methods also include:

[0129] Step 205: When the facial features of the leaker cannot be extracted, the sound information in the preset confidentiality area is obtained.

[0130] Sound information refers to sound clips recorded in a confidential area. Sound information can be obtained through a microphone. The method of obtaining sound information is selected by the staff based on actual conditions and will not be elaborated here.

[0131] Step 206: Determine whether acoustic features can be extracted based on the sound information.

[0132] Acoustic features refer to the characteristic information required to determine the identity of a person through speech recognition technology. Speech recognition technology can be used to determine whether acoustic features can be extracted. The method of extracting acoustic features is common knowledge among people in this field and will not be elaborated here.

[0133] Step 207: When the acoustic features can be extracted, the leakage features of the leaker are determined based on the sound information.

[0134] Being able to extract acoustic features means that the acoustic features in the sound information can be extracted. In this case, the acoustic features in the sound information are extracted through speech recognition technology as leakage features.

[0135] Step 208: When the acoustic feature cannot be extracted, the area number of the confidentiality area is determined according to the confidentiality image.

[0136] The inability to extract acoustic features means that the identity of the person suspected of leaking secrets cannot be identified at this time. The identity of the person suspected of leaking secrets needs to be further determined to reduce the possibility of leaks. The area number refers to a number set artificially to distinguish confidential areas. The area number can be obtained through image recognition technology. The method of identifying the area number is common knowledge among people in this field and will not be elaborated here.

[0137] Step 209: Determine the closing number according to the area number.

[0138] The electric switch is a switch used to control the opening and closing of the entrance and exit of the confidential area. The electric switch is selected by the staff according to the actual situation and will not be described in detail here. The closing number is a number set manually to distinguish the electric switch. The closing number can be obtained from the closing number corresponding table. The closing number corresponding table refers to a data table that records the closing numbers of the electric switches in the confidential area of ​​each area number.

[0139] Step 210: Control the preset electric switch according to the closing number to close the entrance and exit preset in the confidential area.

[0140] When the facial features of the person suspected of leaking secrets cannot be identified from the image, the acoustic features of the person suspected of leaking secrets are identified from the sound clips recorded in the confidential area as a basis for finding the person suspected of leaking secrets. When the acoustic features of the person suspected of leaking secrets cannot be identified from the sound clips, the entrances and exits are closed by electric switches to seal the confidential area, thereby trapping the person suspected of leaking secrets in the confidential area to wait for management personnel to deal with it, thereby reducing information leakage.

[0141] Reference Figure 5 , the leak handling methods also include:

[0142] Step 211: After closing the entrance and exit, obtain a security image outside the entrance and exit.

[0143] The safety image refers to the picture outside the entrance and exit after the electric switch closes the entrance and exit. The safety image can be obtained through the camera. The method of obtaining the safety image is selected by the staff according to the actual situation and will not be elaborated here.

[0144] Step 212: Determine whether there is a person outside the entrance or exit based on the security image.

[0145] Image recognition technology can be used to determine whether there are people outside the entrance and exit. The method of determining whether there are people is common knowledge among people in this field and will not be elaborated here.

[0146] Step 213: When there is a person outside the entrance or exit, the unlocking feature is determined based on the security image.

[0147] The unlocking feature refers to the facial feature of the person outside the entrance. The facial feature in the security image can be extracted through face recognition technology as the unlocking feature. The recognition method of the unlocking feature is common knowledge among people in this field and will not be elaborated here.

[0148] Step 214: Determine the security level based on the unlocking feature.

[0149] The security level refers to a numerical value set manually to show the level of authority of a person. The security level can be obtained by querying the security level correspondence table. The security level correspondence table refers to a data table that records the unlocking features of a person and their corresponding security level.

[0150] Step 215: When the security level is not lower than the preset access threshold, the unlocking number is determined according to the unlocking feature, and the preset electric control switch is controlled according to the closing number to open the entrance and exit preset in the confidential area.

[0151] The access threshold refers to the minimum security level required for personnel to open the entrance and exit. The access threshold is selected by the staff according to the actual situation and will not be described here. If the security level is not lower than the access threshold, it means that the personnel outside the entrance and exit have sufficient authority to lift the blockade of the confidential area, that is, the personnel outside the entrance and exit have the authority to investigate the person suspected of leaking secrets. At this time, the entrance and exit are opened by the electric control switch to facilitate the investigation.

[0152] The unlock number is a number set to distinguish between staff members. The unlock number can be obtained by querying the unlock number corresponding table. The unlock number corresponding table refers to a data table that records the facial features of each staff member and their corresponding unlock numbers.

[0153] Step 216: Record the confidentiality number and the unlocking number in a preset unlocking record table.

[0154] The unlocking record sheet refers to a form used to record the staff's release of the blockade status of the confidential area. The unlocking record sheet is used to facilitate the tracking of staff suspected of collaborating in leaks, thereby reducing the situation of staff stealing and improving the monitoring of staff.

[0155] Reference Figure 6 , the leak handling methods also include:

[0156] Step 217: Obtain leaked information.

[0157] Leaked information refers to confidential information that has been leaked. Leaked information can be manually input by staff or retrieved from the Internet through big data models. The method of obtaining leaked information is selected by staff based on actual conditions and will not be elaborated here.

[0158] Step 218: Determine the leakage number according to the leakage information.

[0159] The leak number refers to the confidentiality number corresponding to the leaked information. The leak number can be retrieved from the confidential information through the big data model. The method for determining the leak number is common knowledge among people in this field and will not be elaborated here.

[0160] Step 219: Find out the leakage feature from the preset leakage record table according to the leakage number.

[0161] The leakage feature is the leakage feature corresponding to the confidentiality number that is consistent with the leakage number found in the leakage record table.

[0162] Step 220: Determine the main suspect number based on the leakage characteristics.

[0163] The main suspect number is the unlocking number of the person suspected of leaking secrets among the staff members based on the leakage characteristics. When the leakage characteristics are facial features, the facial recognition technology is used to determine the main suspect number. When the leakage characteristics are acoustic features, the voice recognition technology is used to determine the main suspect number. The method for determining the main suspect number is common knowledge among people in this field and will not be elaborated here.

[0164] Step 221: Find the secondary suspect number from the preset unlocking record table according to the leak number.

[0165] The secondary suspect number refers to the unlocking number of the staff member who is suspected of collaborating in the leak. The secondary suspect number is the unlocking number corresponding to the confidentiality number in the unlocking record table that is consistent with the leak number.

[0166] Step 222: Generate suspected leak information based on the primary suspect number and the secondary suspect number.

[0167] The suspected leakage information refers to the information set used to display the main suspect number and the secondary suspect number and related information to the management personnel. The suspected leakage information can be generated through a semantic matching model. The method for generating the suspected leakage information is common knowledge among people in this field and will not be elaborated here.

[0168] Step 223: Control the preset management device to display the suspected persons according to the suspected leak information.

[0169] The management device refers to the equipment used to display information to the management personnel. The management device is selected by the staff according to the actual situation and will not be described in detail here. When the message is confirmed to be leaked, the relevant suspected persons are found from the leakage record table and the unlocking record table, so that the management personnel can identify the source of the leak and improve the security of the information.

[0170] Reference Figure 7 , gesture recognition methods include:

[0171] Step 300: When the camera is blocked, control the preset radio wave device to send out preset distance measuring radio waves, and control the preset radio wave device to receive feedback radio waves.

[0172] The radio wave device refers to a device used to emit electromagnetic waves and receive feedback electromagnetic waves. The radio wave device is selected by the staff according to the actual situation and will not be described in detail here. The ranging radio wave is the electromagnetic wave emitted by the radio wave device to detect the behavior of people in the confidential area. The feedback radio wave is the feedback electromagnetic wave received after the radio wave device emits the ranging radio wave. The receiving method of the feedback radio wave is selected by the staff according to the actual situation and will not be described in detail here.

[0173] Step 301: Determine the posture and position of a person according to the feedback radio waves.

[0174] Personnel posture refers to the three-dimensional parameters of personnel in the confidential area, and personnel position refers to the coordinate point of personnel in the confidential area. Personnel posture and personnel position can be obtained through radar technology identification. The identification method of personnel posture and personnel position is common knowledge among people in this field and will not be elaborated here.

[0175] Step 302: When the person's position falls into a preset operation range, determine whether the person is holding a suspicious device based on the person's posture.

[0176] The operation range refers to the position range for operating the security device. The operation range is selected by the staff according to the actual situation and will not be described here. If the position of a person falls into the operation range, it means that the person in the confidential area is interacting with the security device at this time. It is necessary to judge the person's posture to identify whether the person is performing sensitive behavior.

[0177] A suspicious device refers to a device held by a person in a confidential area. Human posture detection technology can be used to determine whether a person is holding a suspicious device. The method for determining whether a person is holding a suspicious device is common knowledge among people in this field and will not be elaborated here.

[0178] Step 303: When a person holds a suspected device, a preset security device is controlled to issue a preset leakage warning.

[0179] If a person is holding a suspicious device, it means that the person is suspected of filming, and a leak warning will be issued through the confidentiality device.

[0180] Step 304: When the person is not holding the suspected device, determine the operating position of the person's hand according to the person's posture.

[0181] If a person does not hold the suspected device, it means that the person is suspected of filming, and further analysis of the person's behavior is required. The operating position refers to the coordinate position of the person's hand, and the operating position can be extracted from the person's posture. The method of extracting the operating position is common knowledge among people in this field and will not be elaborated here.

[0182] Step 305: When the operation position does not fall within the preset hand interval, the preset security device is controlled to issue a preset leakage warning.

[0183] The hand interval refers to the position interval of the hand when the personnel normally interact with the security device. The hand interval is selected by the staff according to the actual situation and will not be described here. If the operation position does not fall into the hand interval, it means that the personnel is suspected of invading the security device to leak secrets. At this time, a leak warning is issued through the security device.

[0184] When the camera is blocked, the behavior of people is monitored through electromagnetic waves, so that leakage warnings can be issued in time when people perform sensitive behaviors to reduce information leakage.

[0185] Reference Figure 8 , communication interference methods include.

[0186] Step 400: When a person holds a suspected device, the emission direction is determined according to the person's position.

[0187] The emission direction refers to the direction in which electromagnetic waves are emitted by electromagnetic equipment to persons suspected of leaking secrets in a confidential area. The method for determining the emission direction is common knowledge among persons in this field and will not be elaborated here.

[0188] Step 401: Control the preset radio wave device to turn according to the transmission direction, and determine the device volume of the suspected device according to the posture of the person.

[0189] The device volume refers to the volume value of the suspected device. The mass of the suspected device can be estimated based on the postures of the person such as holding with one hand, holding with both hands, and carrying on the back. The device volume of the suspected device can also be estimated based on the mass of the suspected device. The method for determining the device volume is common knowledge among people in this field and will not be elaborated here.

[0190] Step 402: Determine the interference frequency according to the device volume.

[0191] Interference frequency refers to the frequency required to emit electromagnetic waves through radio wave devices to interfere with the use of suspected equipment. The interference frequency can be obtained from the interference frequency correspondence table. The interference frequency correspondence table refers to a data table that records the interference frequencies required by suspected equipment of different device volumes.

[0192] Step 403: Control a preset radio wave device to emit interference radio waves according to the interference frequency.

[0193] The power of a device is often proportional to its volume. The power of the suspected device is estimated based on its volume, and corresponding electromagnetic waves are emitted to the suspected device through radio wave equipment to hinder the operation of the suspected device, thereby reducing information leakage.

[0194] The present invention also includes a lens cleaning method, which includes:

[0195] Step 500: When the camera is blocked, determine the blocked area according to the confidential image.

[0196] The occluded area refers to the range that is blocked in the confidential image. The occluded area can be determined from the confidential image through image recognition technology. The method for determining the occluded area is common knowledge in this field and will not be described in detail here.

[0197] Step 501: Determine the rotation angle of the camera according to the occluded area.

[0198] The rotation angle refers to the angle value at which the camera rotates to reduce the occluded area. The direction opposite to the position of the occluded area in the confidential image can be selected as the direction of camera rotation, and the amplitude of camera rotation can be selected according to the area of ​​the occluded area, so as to obtain the rotation angle by combining the direction and amplitude of camera rotation.

[0199] Step 502: Control the preset camera rotation according to the rotation angle, and reacquire the rotated image.

[0200] The rotated image refers to the picture of the confidential area obtained after the camera is rotated according to the rotation angle. The method for obtaining the rotated image is selected by the staff according to the actual situation and will not be elaborated here.

[0201] Step 503: Determine the transformed area according to the transformed image.

[0202] The post-transformation area refers to the obscured range in the post-transformation image. The post-transformation area can be determined from the post-transformation image by image recognition technology. The method for determining the post-transformation area is common knowledge among those skilled in the art and will not be elaborated here.

[0203] Step 504: Determine an occlusion variable according to the occlusion area and the transformed area.

[0204] The occlusion variable refers to the difference between the area of ​​the occluded region and the area of ​​the transformed region. The occlusion variable is used to show the changing trend of the occluded range in the image.

[0205] Step 505: When the occlusion variable is lower than the preset rotation variable threshold, a cleaning path is determined according to the rotated area.

[0206] The rotation variable threshold refers to the area difference value set manually to determine whether the occluded range in the image changes. The rotation variable threshold is selected by the staff according to the actual situation and will not be described here. If the occlusion variable is lower than the rotation variable threshold, it means that the occluded range in the image changes little, that is, the occluder rotates with the rotation of the lens, which means that the occluder is attached to the camera lens and needs to be processed.

[0207] A drone refers to a device used to clean a camera lens. A cleaning path refers to the route taken by a drone to clean a camera lens. The cleaning path can be automatically generated by a control program supporting the drone according to the area after the rotation. The method for determining the drone and the cleaning path is common knowledge among people in this field and will not be elaborated here.

[0208] Step 506: Control the preset drone to spray the post-transfer area according to the cleaning path, and control the preset drone to wipe the post-transfer area according to the cleaning path.

[0209] Use the drone to spray and wipe the camera lens to clear any obstructions on the lens.

[0210] Step 507: After wiping, obtain a post-wiping image.

[0211] The post-wiping image refers to the picture obtained by the camera after the drone sprays and wipes the camera lens. The method for obtaining the post-wiping image is selected by the staff according to the actual situation and will not be elaborated here.

[0212] Step 508: Determine the foreign matter area according to the converted image and the wiped image.

[0213] The foreign matter area refers to the obscured range in the wiped image. The foreign matter area can be determined from the wiped image by image recognition technology. The method for determining the foreign matter area is common knowledge among those skilled in the art and will not be elaborated here.

[0214] Step 509: Determine a removal path according to the foreign matter area.

[0215] The removal path refers to the route taken by the drone to clean the camera lens. The removal path can be automatically generated according to the foreign matter area through the control program of the drone. The method for determining the removal path is common knowledge among people in this field and will not be elaborated here.

[0216] Step 510: Control the preset drone to spray the foreign matter area according to the removal path, and control the preset drone to dry the foreign matter area according to the removal path.

[0217] When the drone sprays and wipes the lens, the stains on the lens can be easily removed. If there are still areas of foreign matter on the lens at this time, it means that there are adhesions on the lens. The drone can repeatedly spray and dry the lens to reduce the stickiness of the adhesions, thereby removing the adhesions from the lens.

[0218] Based on the same inventive concept, an embodiment of the present invention provides a security system based on artificial intelligence, including:

[0219] An acquisition module is used to acquire confidential images, network parameters, display parameters, confidential numbers, sound information, security images and leaked information;

[0220] A memory for storing a program of any one of the above-mentioned artificial intelligence-based confidentiality methods;

[0221] The program in the memory can be loaded and executed by the processor.

[0222] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any of the above-mentioned artificial intelligence-based confidentiality methods.

[0223] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0224] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A confidentiality method based on artificial intelligence, characterized in that: include: Acquire a confidential image within a preset confidential area; Determine whether the camera is blocked based on the confidential image; When the camera is blocked, the preset security device is controlled to issue a preset blocking warning; When the camera is not blocked, determine whether there is a camera device based on the confidential image; When there is a camera device, the preset security device is controlled to issue a preset leakage warning.

2. The artificial intelligence-based confidentiality method according to claim 1, characterized in that: Also includes: Control the preset security device to obtain network parameters; Determine whether the security device is disconnected from the network based on network parameters; When the security device is disconnected from the network, the preset security device is controlled to issue a preset disconnection warning; When the security device is not disconnected from the network, the preset security device is controlled to obtain display parameters; Determine the display number according to the display parameters; Determine confidentiality level based on display number; When the confidentiality level is lower than a preset display threshold, the preset confidentiality device is controlled to issue a preset leakage warning.

3. The artificial intelligence-based confidentiality method according to claim 2, characterized in that: Also included is a method for handling confidentiality leaks, the method comprising: When the preset security device issues a preset leakage warning, obtaining the security number currently displayed by the preset security device; Determine whether the facial features of the leaker can be extracted based on the confidential image; When the facial features of the leaker can be extracted, the leaking features of the leaker are determined based on the confidential image; Determine the breach based on confidential images; Record confidentiality numbers, leakage characteristics and leakage behaviors in the preset leakage record table.

4. The method for maintaining confidentiality based on artificial intelligence according to claim 3, characterized in that: The leakage handling method also includes: When the facial features of the leaker cannot be extracted, the sound information in the preset confidential area is obtained; Determine whether acoustic features can be extracted based on the sound information; When the acoustic features can be extracted, the leaking features of the leaker are determined based on the sound information; When the acoustic feature cannot be extracted, the region number of the confidentiality region is determined based on the confidentiality image; Determine the closing number based on the area number; The preset electric switch is controlled according to the closing number to close the entrance and exit preset in the confidential area.

5. The method for maintaining confidentiality based on artificial intelligence according to claim 4, characterized in that: The leakage handling method also includes: After closing the entrance and exit, obtain the security image outside the entrance and exit; Determine whether there are people outside the entrance or exit based on the security image; When there is a person outside the entrance or exit, the unlocking feature is determined based on the security image; Determine security level based on unlocking characteristics; When the security level is not lower than the preset access threshold, the unlocking number is determined according to the unlocking feature, and the preset electric control switch is controlled to open the entrance and exit preset in the confidential area according to the closing number; Record the confidentiality number and unlocking number in the preset unlocking record table.

6. The method for maintaining confidentiality based on artificial intelligence according to claim 5, characterized in that: The leakage handling method also includes: Obtaining confidential information; Determine the leak number based on the leak information; Find out the leakage characteristics from the preset leakage record table according to the leakage number; Determine the main suspect number based on the characteristics of the leak; Find the secondary suspect number from the preset unlocking record table according to the leak number; Generate suspected leak information based on the main suspect number and the secondary suspect number; The suspected persons are displayed according to the preset management device of the suspected information leakage control.

7. The method for maintaining confidentiality based on artificial intelligence according to claim 1, characterized in that: Also included is a gesture recognition method, the gesture recognition method comprising: When the camera is blocked, the preset radio wave device is controlled to send out preset distance measuring radio waves, and the preset radio wave device is controlled to receive feedback radio waves; Determine the personnel's posture and position based on the feedback radio waves; When the person's position falls into the preset operation range, determine whether the person is holding a suspicious device based on the person's posture; When a person holds a suspected device, the preset confidentiality device is controlled to issue a preset leakage warning; When the person is not holding the suspected device, determine the operating position of the person's hand based on the person's posture; When the operating position does not fall within the preset hand interval, the preset security device is controlled to issue a preset leakage warning.

8. The method for maintaining confidentiality based on artificial intelligence according to claim 7, characterized in that: Also included is a communication interference method, the communication interference method comprising: When a person is holding a suspected device, determine the direction of the launch based on the person's position; Control the preset radio wave device to turn according to the emission direction, and determine the device size of the suspected device according to the posture of the personnel; Determine the interference frequency based on the size of the equipment; The preset radio wave device is controlled to emit interference radio waves according to the interference frequency.

9. An artificial intelligence-based confidentiality system, characterized in that: include: An acquisition module is used to acquire confidential images, network parameters, display parameters, confidential numbers, sound information, security images and leaked information; A memory for storing a program of the artificial intelligence-based confidentiality method according to any one of claims 1 to 8; The program in the memory can be loaded and executed by the processor.

10. An intelligent terminal, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes the artificial intelligence-based confidentiality method as described in any one of claims 1 to 8.

Images